Perception of Concatenative vs. Neural Text-To-Speech (TTS): Differences in Intelligibility in Noise and Language Attitudes.
Michelle CohnGeorgia ZellouPublished in: INTERSPEECH (2020)
Keyphrases
- text to speech
- signal to noise ratio
- text to speech synthesis
- speech synthesis
- english text
- statistically significant
- attitudes toward
- programming tool
- individual differences
- prosodic features
- word processing
- neural network
- network architecture
- motor control
- random noise
- noise reduction
- noisy data
- language learning
- pattern recognition
- human perception
- gaussian noise
- biologically inspired
- visual processing
- noise level
- associative memory
- missing data